Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Natural Language To Skill · stijnman | DecimalAI

agent toolingby stijnman

Natural Language To Skill

stijnman/natural-language-to-skill

Source stijnman/grok-custom-skills ↗License MIT

Converts natural language descriptions into SKILL.md drafts.

SkillScore70Maintained

Automatic

AI Engineer pack

Last verified 8/15/2026

What it changes

Passed 16 of 23 test cases with the skill, and 5 of 23 without it.

Without skill22%

With skill70%

Checks it passed that the model alone missed

Limits the name to 64 characters
Names the skill definition file SKILL.md
Generates SKILL.md as the main specification file

and 10 more in the full report

12 fixed4 passed either way6 still failing1 broke

Pass-rate lift: +48 pp
Tokens: -45%
Agent turns: 0%
Response time: -61%

Model gemini-3.6-flashMeasured 8/15/2026v216 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/stijnman-natural-language-to-skill/SKILL.md https://app.decimal.ai/s/stijnman-natural-language-to-skill/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add stijnman-natural-language-to-skill, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/stijnman-natural-language-to-skill/ and pins it in .decimal/skills.lock

decimalai skills add stijnman-natural-language-to-skill

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/stijnman-natural-language-to-skill/SKILL.md https://app.decimal.ai/s/stijnman-natural-language-to-skill/SKILL.md

Raw file: /s/stijnman-natural-language-to-skill/SKILL.md ↗ · machine-readable summary at /s/stijnman-natural-language-to-skill.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

Here are complete details for 'code-linter': Trigger 'lint code', workflow 'run eslint', error 'lint error -> output findings'. What is the precise destination path for storing this skill package?

What was checked, without and with the skill
Checked	Without skill	With skill
Outputs destination path .grok/skills/code-linter/	Missed	Passed

case-18 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md34 linessingle file

Natural Language To Skill

When to Use

User says create skill from description or task matches this capability
User says NL to skill or task matches this capability
User says skill from prompt or task matches this capability

Workflow

Parse intent: triggers, workflow, integrations, errors.
Generate SKILL.md following Agent Skills spec.
Run hyper-skill-tester on draft.
Save to .grok/skills// via skill-creation-enabler.

Integrations

skill-creation-enabler
hyper-skill-tester
skill-researcher

Error Handling

Failure	Response
Vague request	Ask 3 clarifying questions before generating.

Gotchas

Name must be lowercase-hyphen, max 64 chars.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Track record

Benchmark

16 / 23

test cases passed, vs 5 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/15/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/natural-language-to-skill/SKILL.md

View on GitHub ↗

License MITImported 8/15/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Natural Language To Skill

When to Use

Workflow

Integrations

Error Handling

Gotchas

Example

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills